Visibility estimation via deep label distribution learning in cloud environment

The visibility estimation of the environment has great research and application value in the fields of production. To estimate the visibility, we can utilize the camera to obtain some images as evidence. However, the camera only solves the image acquisition problem, and the analysis of image visibility requires strong computational power. To realize effective and efficient visibility estimation, we employ the cloud computing technique to realize high-through image analysis. Our method combines cloud computing and image-based visibility estimation into a powerful and efficient monitoring framework. To train an accurate model for visibility estimation, it is important to obtain the precise ground truth for every image. However, the ground-truth visibility is difficult to be labeled due to its high ambiguity. To solve this problem, we associate a label distribution to each image. The label distribution contains all the possible visibilities with their probabilities. To learn from such annotation, we employ a CNN-RNN model for visibility-aware feature extraction and a conditional probability neural network for distribution prediction. The estimation result can be improved by fusing the predicting results of multiple images from different views. Our experiment shows that labeling the image with visibility distribution can boost the learning performance, and our method can obtain the visibility from the image efficiently.

Experimental Evaluation of PSO Based Transfer Learning Method for Meteorological Visibility Estimation

Estimation of Meteorological visibility from image characteristics is a challenging problem in the research of meteorological parameters estimation. Meteorological visibility can be used to indicate the weather transparency and this indicator is important for transport safety. This paper summarizes the outcomes of the experimental evaluation of a Particle Swarm Optimization (PSO) based transfer learning method for meteorological visibility estimation method. This paper proposes a modified approach of the transfer learning method for visibility estimation by using PSO feature selection. Image data are collected at fixed location with fixed viewing angle. The database images were gone through a pre-processing step of gray-averaging so as to provide information of static landmark objects for automatic extraction of effective regions from images. Effective regions are then extracted from image database and the image features are then extracted from the Neural Network. Subset of Image features are selected based on the Particle Swarming Optimization (PSO) methods to obtain the image feature vectors for each effective sub-region. The image feature vectors are then used to estimate the visibilities of the images by using the Multiple Support Vector Regression (SVR) models. Experimental results show that the proposed method can give an accuracy more than 90% for visibility estimation and the proposed method is effective and robust.

Vision-based Visibility Estimation: From Fog Detection to Complete Visual Range

<p>In air traffic management (ATM) and monitoring of critical infrastructure, the exact description of the near surface atmospheric state - and thus the visibility - is an indispensable basis for situation awareness and any further weather forecast.</p><p>In order to overcome the drawbacks of the currently subjective reports from human observers, we present an innovative solution to automatically derive visibility measures from standard cameras by a vision based approach.</p><p>The certified state of the art for automated visibility measurement is represented by visibility sensors, such as those e.g. used for RVR (Runway Visual Range) measurements. These sensors only allow a very local measurement, whereas camera-based methods enable a representative measurement of the visibility in the entire environment of the camera location. A variety of camera-based approaches use physically based models to derive a measure of visibility (e.g. the Koschmieder model or contrast measurements, as well as models for measuring light reduction). The Dutch weather service (KNMI) uses similar visibility detectors and methods as are used for our system called “visIvis®” (e.g. feature-based methods or de-hazing methods). In addition to the restriction to a single specific method, often additional special requirements (e.g. the measurement object or the land mark must lie on a straight line with two cameras) complicate the use of these methods for a representative measurement of the entire scene.</p><p>It will be shown how the visIvis® system can detect automatically most suitable areas for visibility estimation within the camera-covered range based on a variety of detection algorithms, automatically tunes its detection parameters, and automatically derives fog covered areas. Furthermore, by coupling visIvis® with georeferenced data, a pixel-precise depth map is deduced from digital surface and terrain models and user orientated visibility classes can be defined (customized or according to meteorological relevant thresholds). Based on this mapping, visIvis® is able to derive representative visibility measures for complete visual range, that can be reported in customized or standard formats (e.g. METAR).</p><p>The presentation will give insight on a recent visibility measurement study for synoptic meteorological applications in cooperation with Deutscher Wetterdienst (DWD), the German National Meteorological Service. Special focus was laid on night scenarios, which pose challenges on a camera based measurement system, e.g. light sensitivity of the sensor or availability of representative landmarks. In addition, we will show how to generate added value by extending the concept of vision-based visibility measurement to other weather-related parameters. In the present study it was investigated, which steps are required by transfer learning principles to adapt the system towards other camera-based observations. Results will be presented from evaluations in different challenging application scenarios.</p>

Visibility Estimation via Deep Label Distribution Learning

This paper proposes an image-based visibility estimation method with deep label distribution learning. To train an accurate model for visibility estimation, it is important to obtain the precise ground truth for every image. However, the ground-truth visibility is difficult to be labeled due to its high ambiguity. To solve this problem, we associate a label distribution to each image. The label distribution contains all the possible visibilities with their probabilities. To learn from such annotation, we employ a CNN-RNN model for visibility-aware feature extraction and a conditional probability neural network for distribution prediction. Our experiment shows that labeling the image with visibility distribution can not only overcome the inaccurate annotation problem, but also boost the learning performance without the increase of training examples.

Visibility Estimation via Deep Label Distribution Learning

This paper proposes an image-based visibility estimation method with deep label distribution learning. To train an accurate model for visibility estimation, it is important to obtain the precise ground truth for every image. However, the ground-truth visibility is difficult to be labeled due to its high ambiguity. To solve this problem, we associate a label distribution to each image. The label distribution contains all the possible visibilities with their probabilities. To learn from such annotation, we employ a CNN-RNN model for visibility-aware feature extraction and a conditional probability neural network for distribution prediction. Our experiment shows that labeling the image with visibility distribution can not only overcome the inaccurate annotation problem, but also boost the learning performance without the increase of training examples.

A Transfer Learning Method for Meteorological Visibility Estimation Based on Feature Fusion Method

Meteorological visibility is an important meteorological observation indicator to measure the weather transparency which is important for the transport safety. It is a challenging problem to estimate the visibilities accurately from the image characteristics. This paper proposes a transfer learning method for the meteorological visibility estimation based on image feature fusion. Different from the existing methods, the proposed method estimates the visibility based on the data processing and features’ extraction in the selected subregions of the whole image and therefore it had less computation load and higher efficiency. All the database images were gray-averaged firstly for the selection of effective subregions and features extraction. Effective subregions are extracted for static landmark objects which can provide useful information for visibility estimation. Four different feature extraction methods (Densest, ResNet50, Vgg16, and Vgg19) were used for the feature extraction of the subregions. The features extracted by the neural network were then imported into the proposed support vector regression (SVR) regression model, which derives the estimated visibilities of the subregions. Finally, based on the weight fusion of the visibility estimates from the subregion models, an overall comprehensive visibility was estimated for the whole image. Experimental results show that the visibility estimation accuracy is more than 90%. This method can estimate the visibility of the image, with high robustness and effectiveness.